A key challenge in many modern data analysis tasks is that user data are...
We revisit the problem of designing scalable protocols for private stati...
In this work, we study practical heuristics to improve the performance o...
We study the problem of locally private mean estimation of high-dimensio...
We consider online learning problems in the realizable setting, where th...
A canonical algorithm for log-concave sampling is the Langevin Algorithm...
Privately learning statistics of events on devices can enable improved u...
Online prediction from experts is a fundamental problem in machine learn...
Recovering linear subspaces from data is a fundamental and important tas...
Sampling from a high-dimensional distribution is a fundamental task in
s...
The shuffle model of differential privacy has gained significant interes...
Cross-device federated learning is an emerging machine learning (ML) par...
A central issue in machine learning is how to train models on sensitive ...
We study the problem of mean estimation of ℓ_2-bounded vectors under the...
In this work, we propose a new algorithm ProjectiveGeometryResponse (PGR...
Computing the noisy sum of real-valued vectors is an important primitive...
We study adaptive methods for differentially private convex optimization...
Stochastic convex optimization over an ℓ_1-bounded domain is ubiquitous
...
Locally Differentially Private (LDP) Reports are commonly used for colle...
Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and
Th...
Modern machine learning models are complex and frequently encode surpris...
Commonly used classification algorithms in machine learning, such as sup...
Various differentially private algorithms instantiate the exponential
me...
State-of-the-art optimization is steadily shifting towards massively par...
Uniform stability is a notion of algorithmic stability that bounds the w...
We study differentially private (DP) algorithms for stochastic convex
op...
Human learners appreciate that some facts demand memorization whereas ot...
Two commonly arising computational tasks in Bayesian learning are
Optimi...
The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and ...
We study differentially private (DP) algorithms for stochastic convex
op...
We consider convex SGD updates with a block-cyclic structure, i.e. where...
We study the stochastic multi-armed bandits problem in the presence of
a...
Sensitive statistics are often collected across sets of users, with repe...
Differentially Private algorithms often need to select the best amongst ...
Many commonly used learning algorithms work by iteratively updating an
i...
We study the problem of controlling linear time-invariant systems with k...
Machine learning models are often susceptible to adversarial perturbatio...
This paper studies the value of switching actions in the Prediction From...
The rapid adoption of machine learning has increased concerns about the
...
The recent, remarkable growth of machine learning has led to intense int...
Some machine learning applications involve training data that is sensiti...
Machine learning techniques based on neural networks are achieving remar...
TensorFlow is an interface for expressing machine learning algorithms, a...
Empirical Risk Minimization (ERM) is a standard technique in machine
lea...